© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15617
    Prev
    Next
    INDEX
    Explanations

    documentation of math concepts, focusing on splines, lines, and fractional expressions

    oai_token-act-pair · gemini-2.0-flash

    Splines

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sidemargin
    -0.77
     autorytatywna
    -0.71
     Majefty
    -0.68
     صوتيه
    -0.66
    AddTagHelper
    -0.66
     Anaconda
    -0.65
    WebServlet
    -0.65
    Obrázky
    -0.64
    omeness
    -0.62
     الرياضيه
    -0.59
    POSITIVE LOGITS
     pro
    0.51
    ario
    0.46
     kri
    0.43
    DispatchToProps
    0.41
    læg
    0.40
     Reg
    0.40
    โป
    0.40
    VG
    0.39
    فية
    0.39
    leta
    0.38
    Activations Density 4.096%

    No Known Activations